© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196160
    Prev
    Next
    INDEX
    Explanations

    import or using statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guel
    0.42
     GDPPC
    0.41
     reinforcing
    0.41
    ܡ
    0.41
     مزید
    0.40
    ು
    0.40
     avenge
    0.40
    lcii
    0.39
    রাজনৈতিক
    0.39
     განს
    0.39
    POSITIVE LOGITS
    这样的
    0.38
    '
    0.38
    anut
    0.37
    ouc
    0.36
     रहेगी
    0.36
    0.35
    接受
    0.35
     đám
    0.35
     ऐसा
    0.34
    ура
    0.34
    Activations Density 0.001%

    No Known Activations